Text-to-Speech API

The Text-to-Speech (TTS) API allows scripts to generate spoken audio from text using NovelAI’s TTS. Scripts can queue text for speech, control playback, and manage the TTS system.

Basic Usage

Speaking Text

To have text spoken immediately, use the api.v1.tts.speak function:

await api.v1.tts.speak('Hello! This text will be spoken aloud.');

The function will interrupt any currently playing speech and immediately speak the new text.

Queuing Text

To add text to the speech queue without interrupting current playback, use the api.v1.tts.queue function:

// This will be spoken first
await api.v1.tts.speak('First sentence.');

// This will be queued and spoken after the first completes
await api.v1.tts.queue('Second sentence.');
await api.v1.tts.queue('Third sentence.');

Queued text will be spoken in the order it was added, after any currently playing speech completes.

Playback Control

Pausing and Resuming

Control playback with pause and resume functions:

// Pause playback
await api.v1.tts.pause();

// Resume playback
await api.v1.tts.resume();

Toggle Pause State

Toggle between paused and playing states:

// If playing, pause. If paused, resume.
await api.v1.tts.togglePause();

Stopping Playback

Stop all current and queued speech:

await api.v1.tts.stop();

This immediately stops playback and clears the speech queue.